INDEX

Explanations

instances of the word "Miracle" and its variants

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

owi

-0.16

extr

-0.16

illet

-0.15

edu

-0.15

emez

-0.15

MIC

-0.15

onso

-0.15

lut

-0.15

emann

-0.15

-0.14

POSITIVE LOGITS

roring

0.33

iam

0.29

rored

0.28

rors

0.27

acles

0.26

iams

0.25

acle

0.24

rror

0.22

ACLE

0.22

abile

0.22

Activations Density 0.007%

instances of the word "Miracle" and its variants

No Comments

No Known Activations